TAU2
Measured May 29, 2026Source
Score
0.17
Models15 0 
GPT-4.1 nano
OpenAIOpenAIUnited States
GPT-4.1 nano is a lightweight, cost-effective model in the GPT-4 series, optimized for high throughput and low-latency applications. It provides a balance of basic reasoning and coding capabilities at a significantly reduced cost and faster response speed compared to larger models.
FastCheap
Input / 1M tokens
$0.10Output / 1M tokens
$0.40Output tokens/s
155.72First-token seconds
0.43sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.04
Lcr
Measured May 29, 2026Source
Score
0.17
Ifbench
Measured May 29, 2026Source
Score
0.32
Aime 25
Measured May 29, 2026Source
Score
0.24
Aime
Measured May 29, 2026Source
Score
0.24
Math 500
Measured May 29, 2026Source
Score
0.85
Scicode
Measured May 29, 2026Source
Score
0.26
Livecodebench
Measured May 29, 2026Source
Score
0.33
Hle
Measured May 29, 2026Source
Score
0.04
Gpqa
Measured May 29, 2026Source
Score
0.51
Mmlu Pro
Measured May 29, 2026Source
Score
0.66
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
24
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
11.2
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
13
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server